Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study
This paper focuses on the problem of model transferability for machine learning models used to estimate hourly traffic volumes. The presented findings enable not only an increase in the accuracy of existing models but also, simultaneously, reduce the cost of data needed for training the models—makin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2021/9944918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564123869642752 |
|---|---|
| author | Przemysław Sekuła Zachary Vander Laan Kaveh Farokhi Sadabadi Krzysztof Kania Sara Zahedian |
| author_facet | Przemysław Sekuła Zachary Vander Laan Kaveh Farokhi Sadabadi Krzysztof Kania Sara Zahedian |
| author_sort | Przemysław Sekuła |
| collection | DOAJ |
| description | This paper focuses on the problem of model transferability for machine learning models used to estimate hourly traffic volumes. The presented findings enable not only an increase in the accuracy of existing models but also, simultaneously, reduce the cost of data needed for training the models—making statewide traffic volume estimation more economically feasible. Previous research indicates that machine learning volume estimation models that leverage GPS probe data can provide transportation agencies with accurate estimates of hourly traffic volumes—which are fundamental for both operational and planning purposes—and do so with a higher level of accuracy than the prevailing profiling method. However, this approach requires a large dataset for model calibration (i.e., input and continuous count station data), which involves significant monetary investment and data-processing effort. This paper proposes solutions, which allow the model to be prepared using a much smaller dataset, given that a previously collected dataset, which may be gathered in a different place and time period, exists. Based on a broad selection of experiments, the results indicate that the proposed approach is capable of achieving similar model performance while collecting data for a 5 times shorter time period and utilizing 1/4 of the number of continuous count stations. These findings will help reduce the cost of preparing and maintaining the traffic volume models and render the traffic volume estimations more financially appealing. |
| format | Article |
| id | doaj-art-58e33b0f37ef4c3da8e5e049be4bf8e1 |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-58e33b0f37ef4c3da8e5e049be4bf8e12025-02-03T01:11:41ZengWileyJournal of Advanced Transportation2042-31952021-01-01202110.1155/2021/9944918Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case StudyPrzemysław Sekuła0Zachary Vander Laan1Kaveh Farokhi Sadabadi2Krzysztof Kania3Sara Zahedian4Department of Civil and Environmental EngineeringDepartment of Civil and Environmental EngineeringDepartment of Civil and Environmental EngineeringFaculty of Informatics and CommunicationDepartment of Civil and Environmental EngineeringThis paper focuses on the problem of model transferability for machine learning models used to estimate hourly traffic volumes. The presented findings enable not only an increase in the accuracy of existing models but also, simultaneously, reduce the cost of data needed for training the models—making statewide traffic volume estimation more economically feasible. Previous research indicates that machine learning volume estimation models that leverage GPS probe data can provide transportation agencies with accurate estimates of hourly traffic volumes—which are fundamental for both operational and planning purposes—and do so with a higher level of accuracy than the prevailing profiling method. However, this approach requires a large dataset for model calibration (i.e., input and continuous count station data), which involves significant monetary investment and data-processing effort. This paper proposes solutions, which allow the model to be prepared using a much smaller dataset, given that a previously collected dataset, which may be gathered in a different place and time period, exists. Based on a broad selection of experiments, the results indicate that the proposed approach is capable of achieving similar model performance while collecting data for a 5 times shorter time period and utilizing 1/4 of the number of continuous count stations. These findings will help reduce the cost of preparing and maintaining the traffic volume models and render the traffic volume estimations more financially appealing.http://dx.doi.org/10.1155/2021/9944918 |
| spellingShingle | Przemysław Sekuła Zachary Vander Laan Kaveh Farokhi Sadabadi Krzysztof Kania Sara Zahedian Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study Journal of Advanced Transportation |
| title | Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study |
| title_full | Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study |
| title_fullStr | Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study |
| title_full_unstemmed | Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study |
| title_short | Transferability of a Machine Learning-Based Model of Hourly Traffic Volume Estimation—Florida and New Hampshire Case Study |
| title_sort | transferability of a machine learning based model of hourly traffic volume estimation florida and new hampshire case study |
| url | http://dx.doi.org/10.1155/2021/9944918 |
| work_keys_str_mv | AT przemysławsekuła transferabilityofamachinelearningbasedmodelofhourlytrafficvolumeestimationfloridaandnewhampshirecasestudy AT zacharyvanderlaan transferabilityofamachinelearningbasedmodelofhourlytrafficvolumeestimationfloridaandnewhampshirecasestudy AT kavehfarokhisadabadi transferabilityofamachinelearningbasedmodelofhourlytrafficvolumeestimationfloridaandnewhampshirecasestudy AT krzysztofkania transferabilityofamachinelearningbasedmodelofhourlytrafficvolumeestimationfloridaandnewhampshirecasestudy AT sarazahedian transferabilityofamachinelearningbasedmodelofhourlytrafficvolumeestimationfloridaandnewhampshirecasestudy |